microsoft-sharepoint
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the Membrane CLI (@membranehq/cli) globally via npm. This is the official tool provided by the vendor for managing integrations.
- [COMMAND_EXECUTION]: The skill relies on executing shell commands through the Membrane CLI to perform authentication, connection management, and data operations (e.g.,
membrane login,membrane connection ensure,membrane action run). - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from Microsoft SharePoint, such as file contents, list items, and site metadata, which could potentially contain malicious instructions intended to influence the agent's behavior.
- Ingestion points: External SharePoint data accessed via
list-drive-items,get-file-content,list-list-items, and themembrane requestproxy command. - Boundary markers: None explicitly provided in the skill instructions to delimit external data from agent commands.
- Capability inventory: The skill allows for network operations, file management within SharePoint, and arbitrary API requests via the Membrane CLI.
- Sanitization: The skill instructions do not specify sanitization or validation logic for the content retrieved from SharePoint, relying on the platform's default handling of tool outputs.
Audit Metadata